# Model-Free Episodic Control with State Aggregation

arXiv: https://arxiv.org/abs/2008.09685 · HTML: https://mlsanity.com/paper/2008.09685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 1 of 1)

- [Neural Episodic Control with State Abstraction](https://mlsanity.com/paper/2301.11490/) (2023)

## Abstract (arXiv)

Episodic control provides a highly sample-efficient method for reinforcement learning while enforcing high memory and computational requirements. This work proposes a simple heuristic for reducing these requirements, and an application to Model-Free Episodic Control (MFEC) is presented. Experiments on Atari games show that this heuristic successfully reduces MFEC computational demands while producing no significant loss of performance when conservative choices of hyperparameters are used. Consequently, episodic control becomes a more feasible option when dealing with reinforcement learning tasks.